Evaluation of Voice Communications

1. A method, comprising: receiving, by a computing system, data indicative of a user response to a question; extracting, by the computing system, at least one word from an electronic representation of a voice communication of the user; and adjusting, by the computing system, content of the data indicative of the user response, based on a determination that the extracted word is inconsistent with the user response to the question.

2. The method of claim 1 , wherein the voice communication of the user includes the user response to the question.

3. The method of claim 1 , wherein the voice communication of the user does not include the user response to the question.

4. The method of claim 1 , further comprising: evaluating a customer representative's interaction with the user based on the determination.

5. The method of claim 1 , further including: performing extracting for a plurality of calls to produce a plurality of extracted words; and determining user responses to the question for users corresponding to the plurality of calls; and updating information indicating whether the extracted word is consistent with a particular response to the question.

6. The method of claim 1 , further including: generating a caller voice print from the at least a portion of an electronic representation; and comparing the caller voice print to a known voice print.

7. The method of claim 1 , wherein the extracting includes a segmenting step.

8. The method of claim 7 , wherein the segmenting step includes detecting a caller voice print within the electronic representation, distinct from a voice of a customer representative, and removing one or more portions of the caller voice print in the electronic representation to produce the extracted word.

9. The method of claim 1 , further comprising determining a probability, greater than a particular threshold, that the extracted word and a known word are the same.

10. The method of claim 9 , wherein the determining the probability includes using at least one of: a Gaussian Mixture Model, voice recognition, tone segmentation, fundamental frequency information, vocal energy information, frequency spectral features, formants, linear predictive coding, neural networks, ensembles of classifiers, spectral analyzers, or signal amplifiers.

11. The method of claim 1 , further comprising tracking, by the computing system, a number of negative words spoken by the user over at least a portion of the voice communication.

12. A non-transitory computer-readable medium having instructions stored thereon that are executable by a computing device to perform operations comprising: receiving data indicative of a user response to a question; performing speech recognition on an electronic representation of a voice communication of the user, to determine at least one word spoken by the user in the voice communication; and adjusting content of the data indicative of the user response, based on a determination that the word is inconsistent with the user response.

13. The non-transitory computer-readable medium of claim 12 , wherein the operations further comprise: storing a plurality of known words; and comparing the word to the plurality of known words and determining a match to one of the known words.

14. The non-transitory computer-readable medium of claim 12 , wherein the operations further comprise: classifying the user response as positive or negative; and classifying the word as positive or negative.

15. The non-transitory computer-readable medium of claim 12 , wherein the operations further comprise: scheduling a follow-up action based on the determination.

16. The non-transitory computer-readable medium of claim 12 , wherein the operations further comprise: determining a probability, greater than a particular threshold, that the word and a known word are the same.

17. A system, comprising: one or more processors; and one or more memories having program instructions stored thereon that are executable by the one or more processing to cause the system to perform operations comprising: receiving data indicative of a user response to a question; extracting at least one word from an electronic representation of a voice communication of the user; and adjusting content of the data indicative of the user response, based on a determination that the extracted word is inconsistent with the user response to the question.

18. The system of claim 17 , wherein the adjusting is further based on a number of negative words extracted from the voice communication.

19. The system of claim 17 , wherein the operations further comprise: storing a plurality of known words; and comparing the extracted word to the plurality of known words and determining a match to one of the known words.

20. The system of claim 17 , evaluating a customer representative's interaction with the user based on the determination.